Speech coding with multi-layer networks

Yoshua Bengio, Régis Cardin, Piero Cosi, Renato De Mori

Abstract: Combining a structural or knowledge-based approach for describing speech units with neural networks capable of automatically learning relations between acoustic properties and speech units is investigated. The authors show how speech coding can be performed by sets of multilayer neural networks whose execution is decided by a data-driven strategy. Coding is based on phonetic properties characterizing a large population of speakers. Results on speaker-independent recognition of vowels using an ear model for preprocessing are reported.<